shunting314andGitHub 8b141ed8c3 full cudagraph for flex-attn (#36298) ...

Signed-off-by: shunting314 <shunting@meta.com>

2026-04-02 21:15:01 -07:00

..

attention

[Kernel] Fuse FP8 output quantization into merge_attn_states (#36518)

2026-04-03 01:47:04 +00:00

core

Feature/silu block quant fusion v1 (#32996)

2026-04-01 18:50:43 +00:00

helion

…

ir

…

mamba

…

moe

[CPU] Support gelu act in cpu_fused_moe (#38770)

2026-04-02 14:14:32 +08:00

quantization

…

__init__.py

…

allclose_default.py

…

quant_utils.py

…

test_apply_repetition_penalties.py

…

test_awq_int4_to_int8.py

…

test_cache_kernels.py

…

test_concat_mla_q.py

…

test_cp_gather_fp8.py

…

test_fla_layernorm_guard.py

…

test_flex_attention.py

full cudagraph for flex-attn (#36298)

2026-04-02 21:15:01 -07:00

test_fused_gdn_post_conv.py

[Perf] fuse kernels in gdn (#37813)

2026-04-02 11:52:18 +00:00

test_fused_quant_activation.py

…

test_fused_recurrent_packed_decode.py

…

test_fused_sigmoid_gating_delta_rule.py

…

test_onednn.py

…

test_shuffle_rows.py

…

test_top_k_per_row.py

…

utils.py

…